集成随机惯性权重和差分变异操作的樽海鞘群算法  

Salp Swarm Algorithm with Random Inertia Weight and Differential Mutation Operator

作　　者：张志强[1] 鲁晓锋[1] 隋连升[1] 李军怀[1] ZHANG Zhi-qiang;LU Xiao-feng;SUI Lian-sheng;LI Jun-huai(School of Computer Science&Engineering,Xi’an University of Technology,Xi’an 710048,China)

机构地区：[1]西安理工大学计算机科学与工程学院,西安710048

出　　处：《计算机科学》2020年第8期297-301,共5页Computer Science

基　　金：陕西省教育厅自然科学研究项目(18JK0557);陕西省科技计划项目(2018HJCG-05);西安市科技计划项目(201805037YD15CG21(4))。

摘　　要：为了提高樽海鞘群算法(Salp Swarm Algorithm,SSA)的收敛速度、计算精度和全局优化能力,在分析总结粒子群优化(Particle Swarm Optimization,PSO)和差分进化(Differential Evolution,DE)算法相关研究成果后,提出了一种集成PSO算法随机惯性权重和DE算法差分变异操作的改进SSA算法——iSSA。首先,将PSO算法的随机惯性权重引入SSA算法的追随者位置更新公式中,用于增强和平衡SSA算法的勘探与开发能力;其次,用DE算法的变异操作替代SSA算法的领导者位置更新操作,以提高SSA算法的收敛速度和计算精度。为了检验随机惯性权重和差分变异操作对SSA算法的改进效果,在多个高维基准函数上进行了仿真实验,并与其他改进SSA算法进行了比较。实验结果及分析表明,与SSA算法和两个典型的改进SSA算法(ESSA和CASSA)相比,集成随机惯性权重和差分变异操作的iSSA算法,在没有增加算法时间复杂度的情况下,显著地提高了SSA算法的收敛速度、计算精度和全局优化能力,并且优于ESSA算法和CASSA算法。After analyzing and summarizing the related research achievements of particle swarm optimization(PSO)and differential evolution(DE)algorithms,this paper proposes an improved salp swarm algorithm(iSSA)with random inertia weight and differential mutation operator for enhancing the convergence rate,computational accuracy and global optimization of SSA algorithm.Firstly,the random inertia weight of particle swarm optimization is introduced in the followers’position update equation of SSA algorithm in order to enhance and balance the exploration and exploitation ability of SSA algorithm.Secondly,the leader position update of SSA algorithm is replaced with the mutation operator of differential evolution algorithm DE,which is used to improve the convergence rate and computational accuracy of SSA algorithm.For the purpose of checking the improvement effect on SSA algorithm by the random inertia weight and differential mutation operator,simulation experiments on some high-dimension benchmark functions are performed and comparisons between the proposed iSSA and two typical improved SSA algorithms named by enhanced salp swarm algorithm(ESSA)and crazy and adaptive salp swarm algorithm(CASSA)are performed.The experimental results and analysis show that,the proposed iSSA with random inertia weight and differential mutation operator obviously improves the convergence rate,computational accuracy and global optimization when compared with two typical improved ESSA and CASSA algorithms in the case of no any increase in the time complexity of SSA algorithm.

关 键 词：樽海鞘群算法 群体智能 粒子群优化 随机惯性权重 差分进化 变异操作 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]